Volume 8, Issue 5, May – 2023 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
Digital Prescription and Disease Prediction
using Machine Learning
Indrajeet Acharya, Harish Yadav, Abhibhav Jadhav, Nithish Kumar Naicker, Sabanaz S. Peerzade
Dept. of Computer Engineering
Sinhgad College of Engineering, Pune, India
Abstract:- The healthcare industry is increasingly
concerned about medical errors, which are the leading
cause of death worldwide and also compromise patient
safety. This medical error is even more serious in
developing countries where healthcare is not supported
by technology. Because of the traditional paper-based
prescription system, World has an overall 8% – 25%
median medication prescribing error rate that could be
avoided if an electronic prescription system was in place.
Therefore, this study aims to assess physicians’
perceptions towards electronic prescription
implementation.
Accurate and on-time analysis of any health-related
problem is important for the prevention and treatment of
the illness. The traditional way of diagnosis may not be
sufficient in the case of a serious ailment. Developing a
medical diagnosis system based on machine learning
(ML) algorithms for prediction of any disease can help in
a more accurate diagnosis than the conventional method.
We have designed a disease prediction system using
multiple ML algorithms. The dataset used had more than
41 diseases for processing. Based on the symptoms, age,
and gender of an individual, the diagnosis system gives the
output as the disease that the individual might be
suffering from. The Naïve Bayes algorithm gave the best
results as compared to the other algorithms. The accuracy
of the Naïve Bayes algorithm for the prediction was 99%.
Our diagnosis model can act as a doctor for the early
diagnosis of a disease to ensure the treatment can take
place on time and lives can be saved.
Keywords:- Healthcare, Prescription System, Treatment,
Diagnosis, Machine Learning, Symptoms, Naive Bayes.
I. INTRODUCTION
The health care industry has become increasingly
concerned about patient safety, which corresponds to societal
trends [1]. Medication safety is one of the most important
concerning issues in global health policy [2]. Medical error is
a common encounter and represents an important public
health problem posing a serious threat to patient safety. A
medical error is an error occurred in the prescribing,
dispensing, or administration of a drug [4]. It is an avoidable
negative impact of medical care, regardless of whether it is a
visible or detrimental to the patient [4]. The use of an e-
prescriptions has the potential to improve the quality of
patient care at the pharmacy [1]. Indeed, a study shows a
significant improvements associated with an e-prescription
system implementation, including a 86% decrease in serious
medication errors, and an increase in Medicare formulary
adherence from 14% to 88% [11]. e-Prescription is an
IJISRT23MAY572 www.ijisrt.com
alternative to many years old paper-based prescriptions.
Electronic prescribing and dispensing processes of drugs
whether in medical practice, follow up or research has
become an integral partof pharmacy informatics [12]. Despite
the fact that the e- Prescription system is an essential tool for
the healthcare industry, e-Prescription adoption and
utilization remain low in developing countries [13]. Many
healthcare organizations around the world have implemented
electronic information systems to improve the process of
recording information, but only a few have succeeded [14].
Medicine and healthcare are some of the most crucial
parts of the economy and human life. There is a tremendous
amount of change in the world we are livingin now and the
world that existed a few weeks back. Everything has turned
gruesome and divergent. In this situation, where everything
has turned virtual, the doctors and nurses are putting up
maximum efforts to save people’s lives even if they have to
danger their own. There are also some remote villages which
lack medical facilities. Virtual doctors are board-certified
doctors who choose to practice online via video and phone
appointments, rather than in-person appointments but this is
not possible in the case of emergency. Machines are always
considered better than humans as, without any human error,
they can perform tasks more efficiently and with a consistent
level of accuracy. A disease predictor can be called a virtual
doctor, which can predict the disease of any patient without
any human error. Also, in conditions like COVID-19 and
EBOLA, a disease predictor can be a blessing as it can
identify a human’s disease without any physical contact.
Some models of virtual doctors do exist, but they do not
comprise the required level of accuracy as all the parameters
required are not being considered. The primary goal was to
develop numerous models to define which one of them
provides the most accurate predictions. While ML projects
vary in scale and complexity, their general structure is the
same. Several rule-based techniques were drawn from
machine learning to recall the development and deployment
of the predictive model. Several models were initiated by
using various machine learning (ML) algorithms that
collected raw data and then bifurcated it according to
symptoms.
The data-set was then processed in ML models like
Naive Bayes. According to ML models, the accuracy varied.
While processing the data, the input parameters data-set was
supplied to model, and the disease was received as an output.
3830
Volume 8, Issue 5, May – 2023
II. RELATED WORK
A. General:
A review of literature can be defined as a body of the text
that mainly focuses on review of all the crucial data points
and/or method that gives us a different approach towards a
specific topic. It displays information in a very explicit and
subjective field and typically the info in a very explicit
subject field among a particular or fundamental quantity. Its
final goal is to bring the reader and people up so far with
current literature that is on a subject and forms of the idea for
one or more goal, like future analysis that will be by required
within the space and also precedes a search proposal. There
are numerous work that have been done related to disease
prediction system using different Machine Learning
algorithms and achieved different results for different
methods in medical field.
B. Disease Prediction Using Machine Learning (2020):
Author – Chauhan Raj H.
Description: This system is used to predict disease
according to symptoms. This system uses decision tree
classifier for evaluating the model. This system is used by
end-users. The system will predict disease based on
symptoms. This system uses Machine Learning Technology.
For predicting diseases, the decision tree classifier algorithm
is used. We have named this system as'AI THERAPIST'. This
system is for those people who arealways fretting about their
health, for this reason, we provide some features which
acknowledge them and enhance their mood too. So, there is a
feature for the awareness of health 'Disease Predictor', which
recognize disease according to symptoms.
C. Disease Prediction Using Machine Learning (2019):
Author – Kedar Pingale.
This system is used to predict most of the chronic
diseases. It accepts the structured and textual type of data as
input to the machine learning model. This system is used by
end users. System will predict disease on the basis of
symptoms. This system uses Machine Learning Technology.
For predicting diseases Naïve Bayes algorithm, for clustering
KNN algorithm, final output will be in the form of 0 or 1 for
Fig. 1: Proposed System for Disease Prediction
IJISRT23MAY572 www.ijisrt.com
International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
which Logistic tree is used.
D. Multiple Disease Prediction Using Machine Learning
Algorithms Comparetivily (2020):
Author – Smita S. Gunjal
This paper proposing such a system which will flaunt a
simple and elegant User Interface and also be time efficient.
In order to make it less time consuming we are aiming at a
more specific questionnaire which will be followed by the
system. Our aim with this system is to be the connecting
bridge between doctors and patients. The main feature will
be the machine learning, in which we will be using
algorithms such as Naïve Bayes Algorithm, K-Nearest
Algorithm, Decision Tree Algorithm, Random Forest
Algorithm and Support Vector Machine, which willhelp us in
getting accurate predictions and also will find which
algorithm gives a faster and efficient result by comparatively-
comparing. Another feature that our system will comprise of
is Doctor’s Consultation.
III. PROPOSED SYSTEM
Our project is stand on multiple disease prediction in
accordance with symptoms entered by patient. We are
proposing such a system that will flaunt a simple, cost
effective, elegant User Interface and also be time efficient.
Our proposed system bridges the gap between doctors and
patients which will help both classes of users to achieve their
goal. This system is used to predict diseases according to
symptoms. In this proposed system we are going to take down
five symptoms from the users and evaluate them by applying
algorithms such as Naïve bayes. Also, we are going to ask
our users to enter their login details that we are going to store
in our database so that the user can use this prediction for
future use. Lastly, with the input provided by the user, we will
predict the disease associated to those symptoms and also
provide prescription that could be effective against that
disease in the form of a report that would contain the details
regarding the symptoms provided by the user, the disease
predicted by the algorithms and the required prescription
(along with where to get them).
3831
Volume 8, Issue 5, May – 2023
A. System Implementation
 Loading the Dataset:
 We first load the given dataset
 After that we import the required library packages. Data
Pre-processing
 We do reshape and data augmentations. Defining the
Model
 We define the model as sequential or Functional.
 Now we decide the number of layers to be used, Number
of nodes to be used in the model and also the evaluation
metrics. Compiling the Model.
 It defines the loss function, optimizer, and weights.
Model Fit
 Training Data, Testing Data.
B. System Architecture
Fig. 2: Architecture of Disease Prediction System.
C. Algorithm
 Naïve Bayes
Naive Bayes is an easy however amazingly powerful rule
for prognosticative modelling. One of the simplest ways that
of choosing the foremost probable hypothesis given the info
that we've that we are able to use as our previous information
regarding the matter. Bayes’ Theorem provides how that we
are able to calculate the likelihood of a hypothesis given our
previous information. Naive Bayes classifier assumes that the
presence of a specific feature in an exceedingly class is
unrelated to the presence of the other feature
It is a machine learning algorithm for classification
problems and is based on Bayes’ probability theorem. The
primary use of this is to do text classification which involves
high dimensional training data sets. We used the Bayes
IJISRT23MAY572 www.ijisrt.com
International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
 Objective
A framework for multiple disease predication system
based on the symptoms using Naïve bayes supervised
machine learning algorithms. Also the application interface
which will help the patient and the doctor to stay connected.
 Scope of the Project
The aim of this study is to test the proposed hypothesis
that supervised ML algorithms can improve health care by the
accurate and early detection of diseases. There is a demand to
make such a system that will help end users to predict
diseases on the basis of symptoms given in it without visiting
hospitals. By doing so, it will decrease the rush at OPD‟s of
hospitals and bring down the workload on medical staff.
theorem that can be defined as:
P(d|h) is the probability of data d given that the
hypothesis h was true. P(h) is the probability of hypothesis h
being true (regardless of the data). This is called the prior
probability of h. P(d) is the probability of the data (regardless
of the hypothesis).
IV. RESULT AND DISCUSSION
Now the working and results of our system is displayed
here. Various Screenshots with their explanation can be
shown below on how the system will work and helppeople in
contacting the doctor in no time and predicting the disease.
These are the screenshots of the Digital Prescription and
Disease Prediction Application:
3832
Volume 8, Issue 5, May – 2023 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165

Fig. 3: Start Screen of Digital Prescription

Firstly, When the patient, doctor and pharmacist will open the app they will see this interface. The display isshowing smart
health on the screen and then after few seconds the login page will be displayed to the user.

P(h|d) = P (d|h)·P (h) /P (d)

Where P(h|d) is the probability of hypothesis h given the data d. This is called the posterior probability.

Fig. 4: Registration and Login Page

The register and login page will show the user to select Now the various dashboards from each user can be
the option from Doctor, Patient and Lab/Pharmacy. Here if shown as given below:
the user is new it has to first register and then it canlogin to
the system. Else user can login directly.

IJISRT23MAY572 www.ijisrt.com 3833

Volume 8, Issue 5, May – 2023 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165

Fig. 5: Doctor’s Dashboard

After login doctor can see this dashboard in front of patient. Doctor can create and edit his/her profile accordingto
him/her. Through this doctor can see the history of the the requirement.
patient and add prescription according to the health of the

Fig. 6: Patient’s Dashboard

IJISRT23MAY572 www.ijisrt.com 3834

Volume 8, Issue 5, May – 2023
Patient can see the prescription added by the doctor on his
/her dashboard. Various functions such as Chatbot,
Appointment, Disease Prediction, Doctor list, Order Online
International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
Medicine, Pharmacy Details, Search Medicine and Medicine
Remainder.

Fig. 7: Pharmacist’s Dashboard

Pharmacist can add the details of the medicine, description about the medicine and price rate. The report ofthe test can be
generated and send to the user through mailof the user.

Fig. 8: Chid’s Profile on CareTracker

IJISRT23MAY572 www.ijisrt.com 3835

Volume 8, Issue 5, May – 2023 International Journal of Innovative Science and Research Technology
This is the chatbot which patient can use to get suggestions on some common doubts and medicines.
Fig. 9: Disease Prediction from Symptoms
Here the patient will get the option to input 5 symptoms
and according to the input the model will predict the output
as it is trained from the dataset. Theoutput will be shown in
the output box and accordingly the patient can decide what he
wanted to do. Whether to go to the doctor or do the normal
medications.
V. CONCLUSION
Thus through this application, patient can get
information about his or her health in no time without visiting
the doctor in person. It will save both patient and doctor time.
Patient can treat the common disease on its own. Also, the
perception of the user has a significant impact on the
successful implementation of an e- prescription system. To
be successful in e-prescription system implementation, health
care organizations should improve the computer technical
skill of physicians’ providing training on digital device usage,
and improve internet connectivity. As a limitation, the study
was a cross-sectional which has inherited limitation of a
cross- section study. In addition to this the sample size of the
study was a little bit smaller.
The manuscript presented the technique of predicting
the disease based on the symptoms of an individual patient.
The Naïve Bayes model gave the highest accuracy of 99% for
the prediction of diseases using the above-mentioned factors.
Once the disease is predicted, we could easily manage the
medicine resources required for the treatment. This model
would help in lowering the cost required in dealing with the
disease and would also improve the recovery process.
ACKNOWLEDGMENT
We would like to express our sincere gratitude to all
those who have contributed to the successful completion of
this research paper on the Digital Prescription and disease
Prediction using machine Learning. First and foremost, we
would like to acknowledge our supervisor for providing us
with invaluable guidance and support throughout the partial
completion of project. We are grateful to the facultymembers
who provided us with their insights, feedback, and
suggestions that helped us to refine our research. We would
IJISRT23MAY572 www.ijisrt.com
ISSN No:-2456-2165
also like to acknowledge the support and assistance provided
by the technical staff who helped us to set up andmaintain the
experimental system.
Finally, we would like to extend our heartfelt
appreciation to our families and friends for their
encouragement and unwavering support throughout the
process of writing this research paper.
REFERENCES
[1.] Kauppinen H, Ahonen R, Timonen J. The impact of
electronic prescriptions on medication safety in
Finnish community pharmacies: a survey of
pharmacists. Int J Med Inform. 2017;100:56–62. doi:
10.1016/j.ijmedinf.2017.01.014 [PubMed] [CrossRef]
[Google Scholar]
[2.] Hanna K, Riitta A, Johanna T. The impact of electronic
prescriptions on medication safety in Finnish
community pharmacies: A survey of pharmacists.
2017; [PubMed] [Google Scholar]
[3.] Apple JL. The classification of medication errors. Nurs
Manage. 1976;7(12):23–9. doi: 10.1097/00006247-
197612000-00009 [PubMed] [CrossRef] [Google
Scholar]
[4.] Grober ED, Bohnen JMA. Defining medical error. Can
J Surg. 2005;48(1):39–44. [PMC free article]
[PubMed] [Google Scholar]
[5.] Porterfield A, Engelbert K, Coustasse A. Electronic
prescribing: improving the efficiency and accuracy of
prescribing in the ambulatory care setting. Perspect
Heal Inf Manag [Internet]. 2014. Apr 1;11(Spring):1g–
1g. Available from:
https://pubmed.ncbi.nlm.nih.gov/24808808 [PMC
free article] [PubMed] [Google Scholar]
[6.] Neoh CF, Zainal INA, Hameed MA, Khan TM,
Ming LC. Development and progress of pharmaco
informatics in pharmaceutical and health sciences. J
Young Pharm. 2015;7(3):155–63. [Google Scholar]
[7.] Feldman AM. Understanding Health Care Reform:
Bridging the Gap Between Myth and Reality. CRC
Press; 2011. [Google Scholar]
3836
Volume 8, Issue 5, May – 2023 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
[8.] HASANAIN RA, COOPER H. Solutions to overcome
technical and social barriers to electronic health
records implementation in Saudi public and private
hospitals. J Health Inform Dev Ctries. 2014;8(1).
[Google Scholar]
[9.] ChauhanRaj H., NaikDaksh N. ,Halpati,Rinal A.,
Patel,SagarkumarJ. ,&PrajapatiMr. A.D. (2020).
Disease Prediction using Machine Learning.
International Research Journal of Engineering and
Technology, 7(5), 2000-2002.
[10.] Pingale,Kedar.,Surwase,Sushant.,Kulkarni,Vaibhav.,
Sarage,Saura bh., & Karve, Prof. Abhijeet .(2019).
Disease Prediction using Machine Learning.
International Research Journal of Engineering and
Technology, 6(12), 2810-2813. Dalip Vijay Kumar,
“GPS and GSM based Passenger Tracking System”,
International Journal of Computer Applications (0975
— 8887) Volume 100-No.2, August 2014

IJISRT23MAY572 www.ijisrt.com 3837